Abstract
Fiber-reinforced ultra-high-performance concrete (FR-UHPC) has matured over the past 30 years from niche lab mixes to critical responses for high-performance infrastructure, but capabilities of the community continue lag behind expressed multi-crosscut needs in robust vascular prediction of mechanical performance after exposure to fire across modern concrete families. Extension from the historical empirical and mechanistic modeling to more recent data-driven endeavours along with contributions herein, this study presents and validates a full machine learning-based, interpretable framework for the residual flexural strength (RFS) of FR-UHPC following exposure to elevated temperatures. Utilizing a wide experimental database of 800 three-point bending tests, covering binder chemistry, contents of silica-fume and fly-ash, various fiber types (PVA, steel, basalt), curing regimes, and thermal paths, nine state-of-the-art algorithms including the novel hybrid AegisFusion architecture were benchmarked. AegisFusion is a dual-track neural/tree fusion with MetaSwarm tuning and Bayesian calibration. It achieved superior accuracy and calibrated uncertainty in both hold-out (R² = 0.98, RMSE ≈ 0.52 MPa, VAF = 0.98), and 5-fold (R² = 0.93–0.98; RMSE = 0.28‒0.57, VAF = 0.93‒0.98) testing phases. Rigorous non-parametric testing including Friedman and Nemenyi critical difference analysis, ranked AegisFusion best. Model explainability via SHAP and distance-correlation analysis identified exposure maximum temperature (EMT) and fiber volume content (FV) as dominant drivers of RFS, revealing thresholded and nonlinear interactions that align with known thermo-mechanical degradation mechanisms. This study thus forges a data-centric bridge between the historical experimental foundations of FR-UHPC research and contemporary, uncertainty-aware artificial intelligence tools for resilient infrastructure design.
Data availability
The datasets generated and/or analyzed during the current study are not publicly available due to restrictions imposed by research sponsors, ongoing analysis for future studies, and the necessity to maintain data confidentiality until further validation and publication, but are available from Dr. Arsalan Mahmoodzadeh on reasonable request.
Abbreviations
- R2:
-
Coefficient of determination
- RMSE:
-
Root mean squared Error
- MAPE:
-
Mean absolute percentage error
- VAF:
-
Variance accounted For
- SHAP:
-
SHapley additive explanations value
- CT:
-
Curing time
- EMT:
-
Exposure maximum temperature
- w/c:
-
Water-to-binder ratio
- FVC:
-
Fiber volume content
- SFC:
-
Silica fume content
- FAC:
-
Fly-ash content
- SC:
-
Superplasticizer content
- FT:
-
Fiber type
- AT:
-
Aggregate type
- RFS:
-
Residual flexural strength
- UHPC:
-
Ultra-high performance concrete
- FR-UHPC:
-
Fiber-reinforced ultra-high performance concrete
- FRC:
-
Fiber-reinforced concrete
- ANN:
-
Artificial neural networks
- SVR:
-
Support vector regression
- RFR:
-
Random forest regression
- XGBR:
-
Extreme gradient boosting regression
- NuSVR:
-
Nu-support vector regression
- GPR:
-
Gaussian process regression
- GBR:
-
Gradient boosted regression
- DTR:
-
Decision tree regression
References
Abbas, S., Nehdi, M. L. & Saleem, M. A. Ultra-High Performance Concrete: Mechanical Performance, Durability, Sustainability and Implementation Challenges. Int. J. Concrete Struct. Mater. 10 (3), 271–295. https://doi.org/10.1007/s40069-016-0157-4 (2016).
Azmee, N. M. & Shafiq, N. Ultra-high performance concrete: From fundamental to applications. Case Stud. Constr. Mater. 9, e00197. https://doi.org/10.1016/j.cscm.2018.e00197 (2018).
Bajaber, M. A. & Hakeem, I. Y. UHPC evolution, development, and utilization in construction: a review. J. Mater. Res. Technol. 10, 1058–1074. https://doi.org/10.1016/j.jmrt.2020.12.051 (2021).
Escalante-Tovar, J. D., Abellán-García, J. & Fernández-Gómez, J. Predicting and Unraveling Flexural Behavior in Fiber-Reinforced UHPC Through Based Machine Learning Models. J. Compos. Sci. 9 (7), 333. https://doi.org/10.3390/jcs9070333 (2025).
Zhang, Y., Wang, Z., Xi, M., Zhao, Y. & Liu, J. Data-driven prediction of residual flexural capacity in corroded RC beams using PSO and GA-optimized CatBoost ensemble models. Eng. Res. Express. 7 (3), 035129. https://doi.org/10.1088/2631-8695/adfcb3 (2025).
Xu, Q. et al. Intelligent prediction framework for axial compressive capacity of FRP-RACFST columns. Mater. Today Commun. 41, 110999. https://doi.org/10.1016/j.mtcomm.2024.110999 (2024).
Zhang, Y., Xi, M., Liu, J., Wang, W. & Lyu, X. Axial compressive capacity prediction of coal gangue concrete-filled steel tube stub columns: Genetic programming-augmented code calibration and Bayesian-optimized machine learning. Structures 80, 110119. https://doi.org/10.1016/j.istruc.2025.110119 (2025).
Meng, W. & Khayat, K. H. Effect of Hybrid Fibers on Fresh Properties, Mechanical Properties, and Autogenous Shrinkage of Cost-Effective UHPC. J. Mater. Civ. Eng. 30 (4). https://doi.org/10.1061/(ASCE)MT.1943-5533.0002212 (2018).
Wu, Z., Shi, C., He, W. & Wu, L. Effects of steel fiber content and shape on mechanical properties of ultra high performance concrete. Constr. Build. Mater. 103, 8–14. https://doi.org/10.1016/j.conbuildmat.2015.11.028 (2016).
Nasiri, H., Pourbaba, M. & Lotfollahi Yaghin, M. A. Numerical study on the flexural and shear behavior of steel fiber and high-strength steel combination in ultra‐high‐performance fiber‐reinforced concrete beams under cyclic loading. Struct. Concrete. 26 (3), 3663–3677. https://doi.org/10.1002/suco.202300760 (2025).
Nasrin, S. & Ibrahim, A. Flexural response of Ultra-High-Performance Concrete (UHPC) hybrid bridge deck connections made with local materials. Constr. Build. Mater. 270 (121451). https://doi.org/10.1016/j.conbuildmat.2020.121451 (2021).
Jiao, Y. et al. Mechanical and fracture properties of ultra-high performance concrete (UHPC) containing waste glass sand as partial replacement material. J. Clean. Prod. 277 (123501). https://doi.org/10.1016/j.jclepro.2020.123501 (2020).
Abellán-García, J., Carvajal-Muñoz, J. S. & Ramírez-Munévar, C. Application of ultra-high-performance concrete as bridge pavement overlays: Literature review and case studies. Constr. Build. Mater. 410 (134221). https://doi.org/10.1016/j.conbuildmat.2023.134221 (2024).
Tayeh, B. A., Askar, L. K., Askar, M. & Bakar, B. H. A. Ultra-High-Performance Concrete (UHPC) - Applications Worldwide: A State-of-the-Art Review. J. Eng. Res. Technol. 10 (1). https://doi.org/10.33976/JERT.10.1/2023/2 (2023).
Perry, V. H. Ultra-High-Performance-Concrete Advancements and Industrialization—The Need for Standard Testing. Adv. Civil Eng. Mater. 4 (2), 1–16. https://doi.org/10.1520/ACEM20140028 (2015).
Zhang, K. The Characteristics of Ultra-High Performance Concrete and Its Application in Structures. Highlights Sci. Eng. Technol. 106, 513–518. https://doi.org/10.54097/81ydbq69 (2024).
Teng, L. & Khayat, K. H. Effect of overlay thickness, fiber volume, and shrinkage mitigation on flexural behavior of thin bonded ultra-high-performance concrete overlay slab. Cem. Concr. Compos. 134 (104752). https://doi.org/10.1016/j.cemconcomp.2022.104752 (2022).
Hiew, S. Y., Bin Teoh, K., Raman, S. N., Kong, D. & Hafezolghorani, M. A generalised predictive model for the mechanical properties of mono/hybrid fibre-reinforced ultra-high-performance concrete. Constr. Build. Mater. 426 (136154). https://doi.org/10.1016/j.conbuildmat.2024.136154 (2024).
Xu, Q. et al. An explainable ensemble learning framework for flexible pavement roughness prediction under multi-climate stressors. Case Stud. Constr. Mater. 23 (e05402). https://doi.org/10.1016/j.cscm.2025.e05402 (2025).
Zhang, Y. et al. A metaheuristic-driven categorical boosting framework with interpretability for high-precision prediction of mechanical properties in corroded reinforced concrete beams. Eng. Appl. Artif. Intell. 163, 112804. https://doi.org/10.1016/j.engappai.2025.112804 (2026).
Zhang, J. & Zhao, Y. Prediction of Compressive Strength of Ultra-High Performance Concrete (UHPC) Containing Supplementary Cementitious Materials, in International Conference on Smart Grid and Electrical Automation (ICSGEA), May 2017, 522–525., May 2017, 522–525. (2017). https://doi.org/10.1109/ICSGEA.2017.150
Marani, A., Jamali, A. & Nehdi, M. L. Predicting Ultra-High-Performance Concrete Compressive Strength Using Tabular Generative Adversarial Networks. Materials 13 (21), 4757. https://doi.org/10.3390/ma13214757 (2020).
Alabduljabbar, H. et al. Predicting ultra-high-performance concrete compressive strength using gene expression programming method. Case Stud. Constr. Mater. 18, e02074. https://doi.org/10.1016/j.cscm.2023.e02074 (2023).
Ergen, F. & Katlav, M. Machine and deep learning-based prediction of flexural moment capacity of ultra-high performance concrete beams with/out steel fiber. Asian J. Civil Eng. 25 (6), 4541–4562. https://doi.org/10.1007/s42107-024-01064-2 (2024).
Soni, A. & Nateriya, R. Exploring Ultimate Flexural Strengths of Ultra-High-Performance Concrete (UHPC) Samples through Experimental Analysis in Comparison with Ordinary Concrete Structures, National Academy Science Letters, Nov. (2024). https://doi.org/10.1007/s40009-024-01520-2
Lima, C. A. M., Coelho, A. L. V. & Von Zuben, F. J. Ensembles of support vector machines for regression problems, in Proceedings of the International Joint Conference on Neural Networks. IJCNN’02 (Cat. No.02CH37290), 2381–2386., 2381–2386. (2002). https://doi.org/10.1109/IJCNN.2002.1007514
Qian, Y., Sufian, M., Hakamy, A., Farouk Deifalla, A. & El-said, A. Application of machine learning algorithms to evaluate the influence of various parameters on the flexural strength of ultra-high-performance concrete. Front. Mater. 9 https://doi.org/10.3389/fmats.2022.1114510 (2023).
Das, P. & Kashem, A. Hybrid machine learning approach to prediction of the compressive and flexural strengths of UHPC and parametric analysis with shapley additive explanations. Case Stud. Constr. Mater. 20, e02723. https://doi.org/10.1016/j.cscm.2023.e02723 (2024).
Cortes, C. & Vapnik, V. Support-vector networks. Mach. Learn. 20 (3), 273–297. https://doi.org/10.1007/BF00994018 (1995).
Prasad, D. V. V. & Jaganathan, S. Null-space based facial classifier using linear regression and discriminant analysis method. Cluster Comput. 22 (S4), 9397–9406. https://doi.org/10.1007/s10586-018-2178-z (2019).
Rasmussen, C. E. Gaussian Processes in Machine Learning, 63–71. (2004). https://doi.org/10.1007/978-3-540-28650-9_4
Gad, A. F. Artificial Neural Networks. In Practical Computer Vision Applications Using Deep Learning with CNNs 45–106 (A, 2018). https://doi.org/10.1007/978-1-4842-4167-7_2.
Gayathri, R., Rani, S. U., Čepová, L., Rajesh, M. & Kalita, K. A Comparative Analysis of Machine Learning Models in Prediction of Mortar Compressive Strength, Processes, 10 (7), 1387, (2022). https://doi.org/10.3390/pr10071387
Quinlan, J. R. Induction of decision trees. Mach. Learn. 1 (1), 81–106. https://doi.org/10.1007/BF00116251 (1986).
Ho, T. K. The random subspace method for constructing decision forests. IEEE Trans. Pattern Anal. Mach. Intell. 20 (8), 832–844. https://doi.org/10.1109/34.709601 (1998).
Chen, T. & Guestrin, C. XGBoost, in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Aug. 785–794. (2016). https://doi.org/10.1145/2939672.2939785
Zhang, Y., Wang, H., Liu, J., Liu, F. & Lv, X. Intelligent structural design of composite concrete-encased steel columns based on hybrid machine learning and multiobjective optimization. Structural Concrete Aug. https://doi.org/10.1002/suco.70292 (2025).
Demšar, J. No Title. J. Mach. Learn. Res. 7, 1–30. https://doi.org/10.5555/1248547.1248548 (2006).
Wei, J. et al. Transfer learning framework for the wind pressure prediction of high-rise building surfaces using wind tunnel experiments and machine learning. Build. Environ. 271, 112620. https://doi.org/10.1016/j.buildenv.2025.112620 (2025).
Zhang, Y. et al. Machine Learning-Assisted Sustainable Mix Design of Waste Glass Powder Concrete with Strength–Cost–CO2 Emissions Trade-Offs. Buildings 15 (15), 2640. https://doi.org/10.3390/buildings15152640 (2025).
Wang, K. et al. Exploration of computational formulations for wind-induced interference effects on high-rise buildings via Kolmogorov–Arnold networks. Developments Built Environ. 24 (100770). https://doi.org/10.1016/j.dibe.2025.100770 (2025).
Wang, K., Shen, T., Wei, J., Liu, J. & Hu, W. An intelligent framework for deriving formulas of aerodynamic forces between high-rise buildings under interference effects using symbolic regression algorithms. J. Building Eng. 99 (111614). https://doi.org/10.1016/j.jobe.2024.111614 (2025).
Acknowledgements
The authors extend their appreciation to the Deanship of Research and Graduate Studies at King Khalid University for funding this work through Large Research Project under grant number RGP2/147/45. The authors extend their appreciation to the Deanship of Scientific Research at Northern Border University, Arar, KSA for funding this research work through the project number “NBU-FFR-2026-1161-04”. We would like to express my gratitude to GPT 4o for producing Figures 1, 2, and 3. We assure that these figures are only to show a few steps of the experiments and have no impact on the results and achievements of this paper.
Funding
The authors extend their appreciation to the Deanship of Research and Graduate Studies at King Khalid University for funding this work through Large Research Project under grant number RGP2/147/45. The authors extend their appreciation to the Deanship of Scientific Research at Northern Border University, Arar, KSA for funding this research work through the project number “NBU-FFR-2025-1161-XX“.
Author information
Authors and Affiliations
Contributions
M.K. and A.M. conceptualized the study and designed the research methodology. M.K., A.M., and M.H.E.O. carried out the experimental investigation and data curation. A.M. developed the machine learning models and performed the computational analysis. R.H. and S.P. contributed to the interpretation of results and provided critical technical insights related to fiber-reinforced ultra-high-performance concrete behavior at elevated temperatures. A.A. (Abdulaziz Alghamdi), A.N. (Anwar Ahmed), and I.A. supervised the research, provided resources, and critically reviewed the manuscript for intellectual content. M.K. and A.M. wrote the original draft of the manuscript. All authors reviewed, edited, and approved the final version of the manuscript.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Kewalramani, M., Mahmoodzadeh, A., El Ouni, M.H. et al. Machine learning-based prediction of residual flexural strength in fiber-reinforced ultra-high-performance concrete under elevated temperatures. Sci Rep (2026). https://doi.org/10.1038/s41598-026-43833-w
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-43833-w